agora inbox for [email protected]help / color / mirror / Atom feed
[PATCH v1] solaris: Use versioning scripts instead of -Bsymbolic 1066+ messages / 3 participants [nested] [flat]
* [PATCH v1] solaris: Use versioning scripts instead of -Bsymbolic @ 2022-08-23 08:50 Andres Freund <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Andres Freund @ 2022-08-23 08:50 UTC (permalink / raw) -Bsymbolic causes a lot of "ld: warning: symbol referencing errors" warnings. It's quite easy to add the symbol versioning script, we just need a slightly different parameter name. Discussion: https://postgr.es/m/[email protected] --- src/Makefile.shlib | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/src/Makefile.shlib b/src/Makefile.shlib index 2af6192f0f3..3202b2e67de 100644 --- a/src/Makefile.shlib +++ b/src/Makefile.shlib @@ -188,10 +188,15 @@ ifeq ($(PORTNAME), linux) endif ifeq ($(PORTNAME), solaris) - LINK.shared = $(COMPILER) -shared -Wl,-Bsymbolic + LINK.shared = $(COMPILER) -shared ifdef soname LINK.shared += -Wl,-soname,$(soname) endif + BUILD.exports = ( echo '{ global:'; $(AWK) '/^[^\#]/ {printf "%s;\n",$$1}' $<; echo ' local: *; };' ) >$@ + exports_file = $(SHLIB_EXPORTS:%.txt=%.list) + ifneq (,$(exports_file)) + LINK.shared += -Wl,-M$(exports_file) + endif endif ifeq ($(PORTNAME), cygwin) -- 2.37.0.3.g30cc8d0f14 --aym2ahtpoerge4dw-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v27 5/9] Row pattern recognition patch (executor). @ 2024-12-30 23:53 Tatsuo Ishii <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Tatsuo Ishii @ 2024-12-30 23:53 UTC (permalink / raw) --- src/backend/executor/nodeWindowAgg.c | 1845 +++++++++++++++++++++++++- src/backend/utils/adt/windowfuncs.c | 37 +- src/include/catalog/pg_proc.dat | 6 + src/include/nodes/execnodes.h | 58 + 4 files changed, 1935 insertions(+), 11 deletions(-) diff --git a/src/backend/executor/nodeWindowAgg.c b/src/backend/executor/nodeWindowAgg.c index 70a7025818..2a06676572 100644 --- a/src/backend/executor/nodeWindowAgg.c +++ b/src/backend/executor/nodeWindowAgg.c @@ -36,6 +36,7 @@ #include "access/htup_details.h" #include "catalog/objectaccess.h" #include "catalog/pg_aggregate.h" +#include "catalog/pg_collation_d.h" #include "catalog/pg_proc.h" #include "executor/executor.h" #include "executor/nodeWindowAgg.h" @@ -45,9 +46,11 @@ #include "optimizer/optimizer.h" #include "parser/parse_agg.h" #include "parser/parse_coerce.h" +#include "regex/regex.h" #include "utils/acl.h" #include "utils/builtins.h" #include "utils/datum.h" +#include "utils/fmgroids.h" #include "utils/expandeddatum.h" #include "utils/lsyscache.h" #include "utils/memutils.h" @@ -159,6 +162,33 @@ typedef struct WindowStatePerAggData bool restart; /* need to restart this agg in this cycle? */ } WindowStatePerAggData; +/* + * Set of StringInfo. Used in RPR. + */ +#define STRSET_FROZEN (1 << 0) /* string is frozen */ +#define STRSET_DISCARDED (1 << 1) /* string is scheduled to be discarded */ +#define STRSET_MATCHED (1 << 2) /* string is confirmed to be matched + * with pattern */ + +typedef struct StringSet +{ + StringInfo *str_set; + Size set_size; /* current array allocation size in number of + * items */ + int set_index; /* current used size */ + int *info; /* an array of information bit per StringInfo. + * see above */ +} StringSet; + +/* + * Structure used by check_rpr_navigation() and rpr_navigation_walker(). + */ +typedef struct NavigationInfo +{ + bool is_prev; /* true if PREV */ + int num_vars; /* number of var nodes */ +} NavigationInfo; + static void initialize_windowaggregate(WindowAggState *winstate, WindowStatePerFunc perfuncstate, WindowStatePerAgg peraggstate); @@ -184,6 +214,7 @@ static void release_partition(WindowAggState *winstate); static int row_is_in_frame(WindowAggState *winstate, int64 pos, TupleTableSlot *slot); + static void update_frameheadpos(WindowAggState *winstate); static void update_frametailpos(WindowAggState *winstate); static void update_grouptailpos(WindowAggState *winstate); @@ -195,9 +226,60 @@ static Datum GetAggInitVal(Datum textInitVal, Oid transtype); static bool are_peers(WindowAggState *winstate, TupleTableSlot *slot1, TupleTableSlot *slot2); + +static int WinGetSlotInFrame(WindowObject winobj, TupleTableSlot *slot, + int relpos, int seektype, bool set_mark, + bool *isnull, bool *isout); static bool window_gettupleslot(WindowObject winobj, int64 pos, TupleTableSlot *slot); +static void attno_map(Node *node); +static bool attno_map_walker(Node *node, void *context); +static int row_is_in_reduced_frame(WindowObject winobj, int64 pos); +static bool rpr_is_defined(WindowAggState *winstate); + +static void create_reduced_frame_map(WindowAggState *winstate); +static int get_reduced_frame_map(WindowAggState *winstate, int64 pos); +static void register_reduced_frame_map(WindowAggState *winstate, int64 pos, + int val); +static void clear_reduced_frame_map(WindowAggState *winstate); +static void update_reduced_frame(WindowObject winobj, int64 pos); + +static int64 evaluate_pattern(WindowObject winobj, int64 current_pos, + char *vname, StringInfo encoded_str, bool *result); + +static bool get_slots(WindowObject winobj, int64 current_pos); + +static int search_str_set(WindowAggState *winstate, + StringSet *input_str_set); +static StringSet *generate_patterns(StringSet *input_str_set, + char *pattern, VariablePos *variable_pos, + char tail_pattern_initial); +static int add_pattern(StringInfo old, int old_info, StringSet *new_str_set, + char c, char *pattern, char tail_pattern_initial, + int resultlen); +static int freeze_pattern(StringInfo old, int old_info, + StringSet *new_str_set, + char *pattern, int resultlen); +static char pattern_initial(WindowAggState *winstate, char *vname); +static int do_pattern_match(char *pattern, char *encoded_str, int len); + +static StringSet *string_set_init(void); +static void string_set_add(StringSet *string_set, StringInfo str, int info); +static StringInfo string_set_get(StringSet *string_set, int index, int *flag); +static int string_set_get_size(StringSet *string_set); +static void string_set_discard(StringSet *string_set); +static VariablePos *variable_pos_init(void); +static void variable_pos_register(VariablePos *variable_pos, char initial, + int pos); +static bool variable_pos_compare(VariablePos *variable_pos, + char initial1, char initial2); +static int variable_pos_fetch(VariablePos *variable_pos, char initial, + int index); +static VariablePos *variable_pos_build(WindowAggState *winstate); + +static void check_rpr_navigation(Node *node, bool is_prev); +static bool rpr_navigation_walker(Node *node, void *context); /* * initialize_windowaggregate @@ -774,10 +856,12 @@ eval_windowaggregates(WindowAggState *winstate) * transition function, or * - we have an EXCLUSION clause, or * - if the new frame doesn't overlap the old one + * - if RPR is enabled * * Note that we don't strictly need to restart in the last case, but if * we're going to remove all rows from the aggregation anyway, a restart * surely is faster. + * we restart aggregation too. *---------- */ numaggs_restart = 0; @@ -788,7 +872,8 @@ eval_windowaggregates(WindowAggState *winstate) (winstate->aggregatedbase != winstate->frameheadpos && !OidIsValid(peraggstate->invtransfn_oid)) || (winstate->frameOptions & FRAMEOPTION_EXCLUSION) || - winstate->aggregatedupto <= winstate->frameheadpos) + winstate->aggregatedupto <= winstate->frameheadpos || + rpr_is_defined(winstate)) { peraggstate->restart = true; numaggs_restart++; @@ -862,7 +947,22 @@ eval_windowaggregates(WindowAggState *winstate) * head, so that tuplestore can discard unnecessary rows. */ if (agg_winobj->markptr >= 0) - WinSetMarkPosition(agg_winobj, winstate->frameheadpos); + { + int64 markpos = winstate->frameheadpos; + + if (rpr_is_defined(winstate)) + { + /* + * If RPR is used, it is possible PREV wants to look at the + * previous row. So the mark pos should be frameheadpos - 1 + * unless it is below 0. + */ + markpos -= 1; + if (markpos < 0) + markpos = 0; + } + WinSetMarkPosition(agg_winobj, markpos); + } /* * Now restart the aggregates that require it. @@ -917,6 +1017,14 @@ eval_windowaggregates(WindowAggState *winstate) { winstate->aggregatedupto = winstate->frameheadpos; ExecClearTuple(agg_row_slot); + + /* + * If RPR is defined, we do not use aggregatedupto_nonrestarted. To + * avoid assertion failure below, we reset aggregatedupto_nonrestarted + * to frameheadpos. + */ + if (rpr_is_defined(winstate)) + aggregatedupto_nonrestarted = winstate->frameheadpos; } /* @@ -930,6 +1038,12 @@ eval_windowaggregates(WindowAggState *winstate) { int ret; +#ifdef RPR_DEBUG + elog(DEBUG1, "===== loop in frame starts: aggregatedupto: " INT64_FORMAT " aggregatedbase: " INT64_FORMAT, + winstate->aggregatedupto, + winstate->aggregatedbase); +#endif + /* Fetch next row if we didn't already */ if (TupIsNull(agg_row_slot)) { @@ -945,9 +1059,53 @@ eval_windowaggregates(WindowAggState *winstate) ret = row_is_in_frame(winstate, winstate->aggregatedupto, agg_row_slot); if (ret < 0) break; + if (ret == 0) goto next_tuple; + if (rpr_is_defined(winstate)) + { +#ifdef RPR_DEBUG + elog(DEBUG1, "reduced_frame_map: %d aggregatedupto: " INT64_FORMAT " aggregatedbase: " INT64_FORMAT, + get_reduced_frame_map(winstate, + winstate->aggregatedupto), + winstate->aggregatedupto, + winstate->aggregatedbase); +#endif + + /* + * If the row status at currentpos is already decided and current + * row status is not decided yet, it means we passed the last + * reduced frame. Time to break the loop. + */ + if (get_reduced_frame_map(winstate, winstate->currentpos) + != RF_NOT_DETERMINED && + get_reduced_frame_map(winstate, winstate->aggregatedupto) + == RF_NOT_DETERMINED) + break; + + /* + * Otherwise we need to calculate the reduced frame. + */ + ret = row_is_in_reduced_frame(winstate->agg_winobj, + winstate->aggregatedupto); + if (ret == -1) /* unmatched row */ + break; + + /* + * Check if current row needs to be skipped due to no match. + */ + if (get_reduced_frame_map(winstate, + winstate->aggregatedupto) == RF_SKIPPED && + winstate->aggregatedupto == winstate->aggregatedbase) + { +#ifdef RPR_DEBUG + elog(DEBUG1, "skip current row for aggregation"); +#endif + break; + } + } + /* Set tuple context for evaluation of aggregate arguments */ winstate->tmpcontext->ecxt_outertuple = agg_row_slot; @@ -976,6 +1134,7 @@ next_tuple: ExecClearTuple(agg_row_slot); } + /* The frame's end is not supposed to move backwards, ever */ Assert(aggregatedupto_nonrestarted <= winstate->aggregatedupto); @@ -1199,6 +1358,7 @@ begin_partition(WindowAggState *winstate) winstate->framehead_valid = false; winstate->frametail_valid = false; winstate->grouptail_valid = false; + create_reduced_frame_map(winstate); winstate->spooled_rows = 0; winstate->currentpos = 0; winstate->frameheadpos = 0; @@ -2170,6 +2330,11 @@ ExecWindowAgg(PlanState *pstate) CHECK_FOR_INTERRUPTS(); +#ifdef RPR_DEBUG + elog(DEBUG1, "ExecWindowAgg called. pos: " INT64_FORMAT, + winstate->currentpos); +#endif + if (winstate->status == WINDOWAGG_DONE) return NULL; @@ -2278,6 +2443,17 @@ ExecWindowAgg(PlanState *pstate) /* don't evaluate the window functions when we're in pass-through mode */ if (winstate->status == WINDOWAGG_RUN) { + /* + * If RPR is defined and skip mode is next row, we need to clear + * existing reduced frame info so that we newly calculate the info + * starting from current row. + */ + if (rpr_is_defined(winstate)) + { + if (winstate->rpSkipTo == ST_NEXT_ROW) + clear_reduced_frame_map(winstate); + } + /* * Evaluate true window functions */ @@ -2444,6 +2620,9 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags) TupleDesc scanDesc; ListCell *l; + TargetEntry *te; + Expr *expr; + /* check for unsupported flags */ Assert(!(eflags & (EXEC_FLAG_BACKWARD | EXEC_FLAG_MARK))); @@ -2542,6 +2721,16 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags) winstate->temp_slot_2 = ExecInitExtraTupleSlot(estate, scanDesc, &TTSOpsMinimalTuple); + winstate->prev_slot = ExecInitExtraTupleSlot(estate, scanDesc, + &TTSOpsMinimalTuple); + + winstate->next_slot = ExecInitExtraTupleSlot(estate, scanDesc, + &TTSOpsMinimalTuple); + + winstate->null_slot = ExecInitExtraTupleSlot(estate, scanDesc, + &TTSOpsMinimalTuple); + winstate->null_slot = ExecStoreAllNullTuple(winstate->null_slot); + /* * create frame head and tail slots only if needed (must create slots in * exactly the same cases that update_frameheadpos and update_frametailpos @@ -2723,6 +2912,49 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags) winstate->inRangeAsc = node->inRangeAsc; winstate->inRangeNullsFirst = node->inRangeNullsFirst; + /* Set up SKIP TO type */ + winstate->rpSkipTo = node->rpSkipTo; + /* Set up row pattern recognition PATTERN clause */ + winstate->patternVariableList = node->patternVariable; + winstate->patternRegexpList = node->patternRegexp; + + /* Set up row pattern recognition DEFINE clause */ + winstate->defineInitial = node->defineInitial; + winstate->defineVariableList = NIL; + winstate->defineClauseList = NIL; + if (node->defineClause != NIL) + { + /* + * Tweak arg var of PREV/NEXT so that it refers to scan/inner slot. + */ + foreach(l, node->defineClause) + { + char *name; + ExprState *exps; + + te = lfirst(l); + name = te->resname; + expr = te->expr; + +#ifdef RPR_DEBUG + elog(DEBUG1, "defineVariable name: %s", name); +#endif + winstate->defineVariableList = + lappend(winstate->defineVariableList, + makeString(pstrdup(name))); + attno_map((Node *) expr); + exps = ExecInitExpr(expr, (PlanState *) winstate); + winstate->defineClauseList = + lappend(winstate->defineClauseList, exps); + } + } + + /* + * Build variable_pos + */ + if (winstate->defineInitial) + winstate->variable_pos = variable_pos_build(winstate); + winstate->all_first = true; winstate->partition_spooled = false; winstate->more_partitions = false; @@ -2731,6 +2963,111 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags) return winstate; } +/* + * Rewrite varno of Var nodes that are the argument of PREV/NET so that they + * see scan tuple (PREV) or inner tuple (NEXT). Also we check the arguments + * of PREV/NEXT include at least 1 column reference. This is required by the + * SQL standard. + */ +static void +attno_map(Node *node) +{ + (void) expression_tree_walker(node, attno_map_walker, NULL); +} + +static bool +attno_map_walker(Node *node, void *context) +{ + FuncExpr *func; + int nargs; + bool is_prev; + + if (node == NULL) + return false; + + if (IsA(node, FuncExpr)) + { + func = (FuncExpr *) node; + + if (func->funcid == F_PREV || func->funcid == F_NEXT) + { + /* + * The SQL standard allows to have two more arguments form of + * PREV/NEXT. But currently we allow only 1 argument form. + */ + nargs = list_length(func->args); + if (list_length(func->args) != 1) + elog(ERROR, "PREV/NEXT must have 1 argument but function %d has %d args", + func->funcid, nargs); + + /* + * Check expr of PREV/NEXT aruguments and replace varno. + */ + is_prev = (func->funcid == F_PREV) ? true : false; + check_rpr_navigation(node, is_prev); + } + } + return expression_tree_walker(node, attno_map_walker, NULL); +} + +/* + * Rewrite varno of Var of RPR navigation operations (PREV/NEXT). + * If is_prev is true, we take care PREV, otherwise NEXT. + */ +static void +check_rpr_navigation(Node *node, bool is_prev) +{ + NavigationInfo context; + + context.is_prev = is_prev; + context.num_vars = 0; + (void) expression_tree_walker(node, rpr_navigation_walker, &context); + if (context.num_vars < 1) + ereport(ERROR, + errmsg("row pattern navigation operation's argument must include at least one column reference")); +} + +static bool +rpr_navigation_walker(Node *node, void *context) +{ + NavigationInfo *nav = (NavigationInfo *) context; + + if (node == NULL) + return false; + + switch (nodeTag(node)) + { + case T_Var: + { + Var *var = (Var *) node; + + nav->num_vars++; + + if (nav->is_prev) + { + /* + * Rewrite varno from OUTER_VAR to regular var no so that + * the var references scan tuple. + */ + var->varno = var->varnosyn; + } + else + var->varno = INNER_VAR; + } + break; + case T_Const: + case T_FuncExpr: + case T_OpExpr: + break; + + default: + ereport(ERROR, + errmsg("row pattern navigation operation's argument includes unsupported expression")); + } + return expression_tree_walker(node, rpr_navigation_walker, context); +} + + /* ----------------- * ExecEndWindowAgg * ----------------- @@ -2788,6 +3125,8 @@ ExecReScanWindowAgg(WindowAggState *node) ExecClearTuple(node->agg_row_slot); ExecClearTuple(node->temp_slot_1); ExecClearTuple(node->temp_slot_2); + ExecClearTuple(node->prev_slot); + ExecClearTuple(node->next_slot); if (node->framehead_slot) ExecClearTuple(node->framehead_slot); if (node->frametail_slot) @@ -3148,7 +3487,8 @@ window_gettupleslot(WindowObject winobj, int64 pos, TupleTableSlot *slot) return false; if (pos < winobj->markpos) - elog(ERROR, "cannot fetch row before WindowObject's mark position"); + elog(ERROR, "cannot fetch row: " INT64_FORMAT " before WindowObject's mark position: " INT64_FORMAT, + pos, winobj->markpos); oldcontext = MemoryContextSwitchTo(winstate->ss.ps.ps_ExprContext->ecxt_per_query_memory); @@ -3468,14 +3808,54 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno, WindowAggState *winstate; ExprContext *econtext; TupleTableSlot *slot; - int64 abs_pos; - int64 mark_pos; Assert(WindowObjectIsValid(winobj)); winstate = winobj->winstate; econtext = winstate->ss.ps.ps_ExprContext; slot = winstate->temp_slot_1; + if (WinGetSlotInFrame(winobj, slot, + relpos, seektype, set_mark, + isnull, isout) == 0) + { + econtext->ecxt_outertuple = slot; + return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno), + econtext, isnull); + } + + if (isout) + *isout = true; + *isnull = true; + return (Datum) 0; +} + +/* + * WinGetSlotInFrame + * slot: TupleTableSlot to store the result + * relpos: signed rowcount offset from the seek position + * seektype: WINDOW_SEEK_HEAD or WINDOW_SEEK_TAIL + * set_mark: If the row is found/in frame and set_mark is true, the mark is + * moved to the row as a side-effect. + * isnull: output argument, receives isnull status of result + * isout: output argument, set to indicate whether target row position + * is out of frame (can pass NULL if caller doesn't care about this) + * + * Returns 0 if we successfullt got the slot. false if out of frame. + * (also isout is set) + */ +static int +WinGetSlotInFrame(WindowObject winobj, TupleTableSlot *slot, + int relpos, int seektype, bool set_mark, + bool *isnull, bool *isout) +{ + WindowAggState *winstate; + int64 abs_pos; + int64 mark_pos; + int num_reduced_frame; + + Assert(WindowObjectIsValid(winobj)); + winstate = winobj->winstate; + switch (seektype) { case WINDOW_SEEK_CURRENT: @@ -3542,11 +3922,25 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno, winstate->frameOptions); break; } + num_reduced_frame = row_is_in_reduced_frame(winobj, + winstate->frameheadpos); + if (num_reduced_frame < 0) + goto out_of_frame; + else if (num_reduced_frame > 0) + if (relpos >= num_reduced_frame) + goto out_of_frame; break; case WINDOW_SEEK_TAIL: /* rejecting relpos > 0 is easy and simplifies code below */ if (relpos > 0) goto out_of_frame; + + /* + * RPR cares about frame head pos. Need to call + * update_frameheadpos + */ + update_frameheadpos(winstate); + update_frametailpos(winstate); abs_pos = winstate->frametailpos - 1 + relpos; @@ -3613,6 +4007,14 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno, mark_pos = 0; /* keep compiler quiet */ break; } + + num_reduced_frame = row_is_in_reduced_frame(winobj, + winstate->frameheadpos + relpos); + if (num_reduced_frame < 0) + goto out_of_frame; + else if (num_reduced_frame > 0) + abs_pos = winstate->frameheadpos + relpos + + num_reduced_frame - 1; break; default: elog(ERROR, "unrecognized window seek type: %d", seektype); @@ -3631,15 +4033,13 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno, *isout = false; if (set_mark) WinSetMarkPosition(winobj, mark_pos); - econtext->ecxt_outertuple = slot; - return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno), - econtext, isnull); + return 0; out_of_frame: if (isout) *isout = true; *isnull = true; - return (Datum) 0; + return -1; } /* @@ -3670,3 +4070,1430 @@ WinGetFuncArgCurrent(WindowObject winobj, int argno, bool *isnull) return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno), econtext, isnull); } + +/* + * rpr_is_defined + * return true if Row pattern recognition is defined. + */ +static +bool +rpr_is_defined(WindowAggState *winstate) +{ + return winstate->patternVariableList != NIL; +} + +/* + * ----------------- + * row_is_in_reduced_frame + * Determine whether a row is in the current row's reduced window frame + * according to row pattern matching + * + * The row must has been already determined that it is in a full window frame + * and fetched it into slot. + * + * Returns: + * = 0, RPR is not defined. + * >0, if the row is the first in the reduced frame. Return the number of rows + * in the reduced frame. + * -1, if the row is unmatched row + * -2, if the row is in the reduced frame but needed to be skipped because of + * AFTER MATCH SKIP PAST LAST ROW + * ----------------- + */ +static +int +row_is_in_reduced_frame(WindowObject winobj, int64 pos) +{ + WindowAggState *winstate = winobj->winstate; + int state; + int rtn; + + if (!rpr_is_defined(winstate)) + { + /* + * RPR is not defined. Assume that we are always in the the reduced + * window frame. + */ + rtn = 0; +#ifdef RPR_DEBUG + elog(DEBUG1, "row_is_in_reduced_frame returns %d: pos: " INT64_FORMAT, + rtn, pos); +#endif + return rtn; + } + + state = get_reduced_frame_map(winstate, pos); + + if (state == RF_NOT_DETERMINED) + { + update_frameheadpos(winstate); + update_reduced_frame(winobj, pos); + } + + state = get_reduced_frame_map(winstate, pos); + + switch (state) + { + int64 i; + int num_reduced_rows; + + case RF_FRAME_HEAD: + num_reduced_rows = 1; + for (i = pos + 1; + get_reduced_frame_map(winstate, i) == RF_SKIPPED; i++) + num_reduced_rows++; + rtn = num_reduced_rows; + break; + + case RF_SKIPPED: + rtn = -2; + break; + + case RF_UNMATCHED: + rtn = -1; + break; + + default: + elog(ERROR, "Unrecognized state: %d at: " INT64_FORMAT, + state, pos); + break; + } + +#ifdef RPR_DEBUG + elog(DEBUG1, "row_is_in_reduced_frame returns %d: pos: " INT64_FORMAT, + rtn, pos); +#endif + return rtn; +} + +#define REDUCED_FRAME_MAP_INIT_SIZE 1024L + +/* + * create_reduced_frame_map + * Create reduced frame map + */ +static +void +create_reduced_frame_map(WindowAggState *winstate) +{ + winstate->reduced_frame_map = + MemoryContextAlloc(winstate->partcontext, + REDUCED_FRAME_MAP_INIT_SIZE); + winstate->alloc_sz = REDUCED_FRAME_MAP_INIT_SIZE; + clear_reduced_frame_map(winstate); +} + +/* + * clear_reduced_frame_map + * Clear reduced frame map + */ +static +void +clear_reduced_frame_map(WindowAggState *winstate) +{ + Assert(winstate->reduced_frame_map != NULL); + MemSet(winstate->reduced_frame_map, RF_NOT_DETERMINED, + winstate->alloc_sz); +} + +/* + * get_reduced_frame_map + * Get reduced frame map specified by pos + */ +static +int +get_reduced_frame_map(WindowAggState *winstate, int64 pos) +{ + Assert(winstate->reduced_frame_map != NULL); + Assert(pos >= 0); + + /* + * If pos is not in the reduced frame map, it means that any info + * regarding the pos has not been registered yet. So we return + * RF_NOT_DETERMINED. + */ + if (pos >= winstate->alloc_sz) + return RF_NOT_DETERMINED; + + return winstate->reduced_frame_map[pos]; +} + +/* + * register_reduced_frame_map + * Add/replace reduced frame map member at pos. + * If there's no enough space, expand the map. + */ +static +void +register_reduced_frame_map(WindowAggState *winstate, int64 pos, int val) +{ + int64 realloc_sz; + + Assert(winstate->reduced_frame_map != NULL); + + if (pos < 0) + elog(ERROR, "wrong pos: " INT64_FORMAT, pos); + + if (pos > winstate->alloc_sz - 1) + { + realloc_sz = winstate->alloc_sz * 2; + + winstate->reduced_frame_map = + repalloc(winstate->reduced_frame_map, realloc_sz); + + MemSet(winstate->reduced_frame_map + winstate->alloc_sz, + RF_NOT_DETERMINED, realloc_sz - winstate->alloc_sz); + + winstate->alloc_sz = realloc_sz; + } + + winstate->reduced_frame_map[pos] = val; +} + +/* + * update_reduced_frame + * Update reduced frame info. + */ +static +void +update_reduced_frame(WindowObject winobj, int64 pos) +{ + WindowAggState *winstate = winobj->winstate; + ListCell *lc1, + *lc2; + bool expression_result; + int num_matched_rows; + int64 original_pos; + bool anymatch; + StringInfo encoded_str; + StringSet *str_set; + bool greedy = false; + int64 result_pos, + i; + + /* + * Set of pattern variables evaluated to true. Each character corresponds + * to pattern variable. Example: str_set[0] = "AB"; str_set[1] = "AC"; In + * this case at row 0 A and B are true, and A and C are true in row 1. + */ + + /* initialize pattern variables set */ + str_set = string_set_init(); + + /* save original pos */ + original_pos = pos; + + /* + * Check if the pattern does not include any greedy quantifier. If it does + * not, we can just apply the pattern to each row. If it succeeds, we are + * done. + */ + foreach(lc1, winstate->patternRegexpList) + { + char *quantifier = strVal(lfirst(lc1)); + + if (*quantifier == '+' || *quantifier == '*') + { + greedy = true; + break; + } + } + + /* + * Non greedy case + */ + if (!greedy) + { + num_matched_rows = 0; + + foreach(lc1, winstate->patternVariableList) + { + char *vname = strVal(lfirst(lc1)); + + encoded_str = makeStringInfo(); + +#ifdef RPR_DEBUG + elog(DEBUG1, "pos: " INT64_FORMAT " pattern vname: %s", + pos, vname); +#endif + expression_result = false; + + /* evaluate row pattern against current row */ + result_pos = evaluate_pattern(winobj, pos, vname, + encoded_str, &expression_result); + destroyStringInfo(encoded_str); + + if (!expression_result || result_pos < 0) + { +#ifdef RPR_DEBUG + elog(DEBUG1, "expression result is false or out of frame"); +#endif + register_reduced_frame_map(winstate, original_pos, + RF_UNMATCHED); + return; + } + /* move to next row */ + pos++; + num_matched_rows++; + } +#ifdef RPR_DEBUG + elog(DEBUG1, "pattern matched"); +#endif + register_reduced_frame_map(winstate, original_pos, RF_FRAME_HEAD); + + for (i = original_pos + 1; i < original_pos + num_matched_rows; i++) + { + register_reduced_frame_map(winstate, i, RF_SKIPPED); + } + return; + } + + /* + * Greedy quantifiers included. Loop over until none of pattern matches or + * encounters end of frame. + */ + for (;;) + { + int init_size; + + result_pos = -1; + + /* + * Loop over each PATTERN variable. + */ + anymatch = false; + + /* + * makeStringInfo creates initial data size to be 1024 bytes, which is + * too large for us because we only need the initial data as the + * number PATTERN variables (+null terminate), which is usually less + * than 10 bytes. So we reallocate the initial data size as small as + * the number of PATTERN variables. + */ + encoded_str = makeStringInfo(); + pfree(encoded_str->data); + init_size = list_length(winstate->patternVariableList) + 1; + encoded_str->data = (char *) palloc0(init_size); + encoded_str->maxlen = init_size; + + forboth(lc1, winstate->patternVariableList, lc2, + winstate->patternRegexpList) + { + char *vname = strVal(lfirst(lc1)); +#ifdef RPR_DEBUG + char *quantifier = strVal(lfirst(lc2)); + + elog(DEBUG1, "pos: " INT64_FORMAT " pattern vname: %s quantifier: %s", + pos, vname, quantifier); +#endif + expression_result = false; + + /* evaluate row pattern against current row */ + result_pos = evaluate_pattern(winobj, pos, vname, + encoded_str, &expression_result); + if (expression_result) + { +#ifdef RPR_DEBUG + elog(DEBUG1, "expression result is true"); +#endif + anymatch = true; + } + + /* + * If out of frame, we are done. + */ + if (result_pos < 0) + break; + } + + if (!anymatch) + { + /* none of patterns matched. */ + break; + } + + string_set_add(str_set, encoded_str, 0); + +#ifdef RPR_DEBUG + elog(DEBUG1, "pos: " INT64_FORMAT " encoded_str: %s", + encoded_str->data); +#endif + + /* move to next row */ + pos++; + + if (result_pos < 0) + { + /* out of frame */ + break; + } + } + + if (string_set_get_size(str_set) == 0) + { + /* no match found in the first row */ + register_reduced_frame_map(winstate, original_pos, RF_UNMATCHED); + destroyStringInfo(encoded_str); + return; + } + +#ifdef RPR_DEBUG + elog(DEBUG2, "pos: " INT64_FORMAT " encoded_str: %s", + pos, encoded_str->data); +#endif + + /* look for matching pattern variable sequence */ +#ifdef RPR_DEBUG + elog(DEBUG1, "search_str_set started"); +#endif + num_matched_rows = search_str_set(winstate, str_set); + +#ifdef RPR_DEBUG + elog(DEBUG1, "search_str_set returns: %d", num_matched_rows); +#endif + string_set_discard(str_set); + + /* + * We are at the first row in the reduced frame. Save the number of + * matched rows as the number of rows in the reduced frame. + */ + if (num_matched_rows <= 0) + { + /* no match */ + register_reduced_frame_map(winstate, original_pos, RF_UNMATCHED); + } + else + { + register_reduced_frame_map(winstate, original_pos, RF_FRAME_HEAD); + + for (i = original_pos + 1; i < original_pos + num_matched_rows; i++) + { + register_reduced_frame_map(winstate, i, RF_SKIPPED); + } + } + + return; +} + +/* + * search_str_set + * + * Perform pattern matching using "pattern" against input_str_set. pattern is + * a regular expression string derived from PATTERN clause. Note that the + * regular expression string is prefixed by '^' and followed by initials + * represented in a same way as str_set. str_set is a set of StringInfo. Each + * StringInfo has a string comprising initials of pattern variable strings + * being true in a row. The initials are one of [a-z], parallel to the order + * of variable names in DEFINE clause. Suppose DEFINE has variables START, UP + * and DOWN. If PATTERN has START, UP+ and DOWN, then the initials in PATTERN + * will be 'a', 'b' and 'c'. The "pattern" will be "^ab+c". + * + * variable_pos is an array representing the order of pattern variable string + * initials in PATTERN clause. For example initial 'a' potion is in + * variable_pos[0].pos[0] = 0. Note that if the pattern is "START UP DOWN UP" + * (UP appears twice), then "UP" (initial is 'b') has two position 1 and + * 3. Thus variable_pos for b is variable_pos[1].pos[0] = 1 and + * variable_pos[1].pos[1] = 3. + * + * Returns the longest number of the matching rows (greedy matching) if + * quatifier '+' or '*' is included in "pattern". + */ +static +int +search_str_set(WindowAggState *winstate, StringSet *input_str_set) +{ + char *pattern; /* search regexp pattern */ + VariablePos *variable_pos; + int set_size; /* number of rows in the set */ + int resultlen; + int index; + StringSet *new_str_set; + int new_str_size; + int len; + int info; + char tail_pattern_initial; + + /* + * Set last initial char to tail_pattern_initial if we can apply "tail + * pattern initial optimization". If the last regexp component in pattern + * is with '+' quatifier, set the initial to tail_pattern_initial. For + * example if pattern = "ab+", tail_pattern_initial will be 'b'. + * Otherwise, tail_pattern_initial is '\0'. + */ + pattern = winstate->pattern_str->data; + if (pattern[strlen(pattern) - 1] == '+') + tail_pattern_initial = pattern[strlen(pattern) - 2]; + else + tail_pattern_initial = '\0'; + + /* + * Generate all possible pattern variable name initials as a set of + * StringInfo named "new_str_set". For example, if we have two rows + * having "ab" (row 0) and "ac" (row 1) in the input str_set, new_str_set + * will have set of StringInfo "aa", "ac", "ba" and "bc" in the end. + */ + variable_pos = winstate->variable_pos; + new_str_set = generate_patterns(input_str_set, pattern, variable_pos, + tail_pattern_initial); + + /* + * Perform pattern matching to find out the longest match. + */ + new_str_size = string_set_get_size(new_str_set); + len = 0; + resultlen = 0; + set_size = string_set_get_size(input_str_set); + + for (index = 0; index < new_str_size; index++) + { + StringInfo s; + + s = string_set_get(new_str_set, index, &info); + if (s == NULL) + continue; /* no data */ + + /* + * If the string is scheduled to be discarded, we just disregard it. + */ + if (info & STRSET_DISCARDED) + continue; + + len = do_pattern_match(pattern, s->data, s->len); + if (len > resultlen) + { + /* remember the longest match */ + resultlen = len; + + /* + * If the size of result set is equal to the number of rows in the + * set, we are done because it's not possible that the number of + * matching rows exceeds the number of rows in the set. + */ + if (resultlen >= set_size) + break; + } + } + + /* we no longer need new string set */ + string_set_discard(new_str_set); + + return resultlen; +} + +/* + * generate_patterns + * + * Generate all possible pattern variable name initials in 'input_str_set' as + * a set of StringInfo and return it. For example, if we have two rows having + * "ab" (row 0) and "ac" (row 1) in 'input str_set', returned StringSet will + * have set of StringInfo "aa", "ac", "ba" and "bc" in the end. + * 'variable_pos' and 'tail_pattern_initial' are used for pruning + * optimization. + */ +static +StringSet * +generate_patterns(StringSet *input_str_set, char *pattern, + VariablePos *variable_pos, char tail_pattern_initial) +{ + StringSet *old_str_set, + *new_str_set; + int index; + int set_size; + int old_set_size; + int info; + int resultlen; + StringInfo str; + int i; + char *p; + + new_str_set = string_set_init(); + set_size = string_set_get_size(input_str_set); + if (set_size == 0) /* if there's no row in input, return empty + * set */ + return new_str_set; + + resultlen = 0; + + /* + * Generate initial new_string_set for input row 0. + */ + str = string_set_get(input_str_set, 0, &info); + p = str->data; + + /* + * Loop over each new pattern variable char. + */ + while (*p) + { + StringInfo new = makeStringInfo(); + + /* add pattern variable char */ + appendStringInfoChar(new, *p); + /* add new one to string set */ + string_set_add(new_str_set, new, 0); + p++; /* next pattern variable */ + } + + /* + * Generate new_string_set for each input row. + */ + for (index = 1; index < set_size; index++) + { + /* previous new str set now becomes old str set */ + old_str_set = new_str_set; + new_str_set = string_set_init(); /* create new string set */ + /* pick up input string */ + str = string_set_get(input_str_set, index, &info); + old_set_size = string_set_get_size(old_str_set); + + /* + * Loop over each row in the previous result set. + */ + for (i = 0; i < old_set_size; i++) + { + char last_old_char; + int old_str_len; + int old_info; + StringInfo old; + + old = string_set_get(old_str_set, i, &old_info); + p = old->data; + old_str_len = old->len; + if (old_str_len > 0) + last_old_char = p[old_str_len - 1]; + else + last_old_char = '\0'; + + /* Can this old set be discarded? */ + if (old_info & STRSET_DISCARDED) + continue; /* discard the old string */ + + /* Is this old set frozen? */ + else if (old_info & STRSET_FROZEN) + { + /* if shorter match. we can discard it */ + if (old_str_len < resultlen) + continue; /* discard the shorter string */ + + /* move the old set to new_str_set */ + string_set_add(new_str_set, old, old_info); + old_str_set->str_set[i] = NULL; + continue; + } + + /* + * loop over each pattern variable initial char in the input set. + */ + for (p = str->data; *p; p++) + { + /* + * Optimization. Check if the row's pattern variable initial + * character position is greater than or equal to the old + * set's last pattern variable initial character position. For + * example, if the old set's last pattern variable initials + * are "ab", then the new pattern variable initial can be "b" + * or "c" but can not be "a", if the initials in PATTERN is + * something like "a b c" or "a b+ c+" etc. This optimization + * is possible when we only allow "+" quantifier. + */ + if (variable_pos_compare(variable_pos, last_old_char, *p)) + + /* + * Satisfied the condition. Add new pattern char to + * new_str_set if it looks good. + */ + resultlen = add_pattern(old, old_info, new_str_set, *p, + pattern, tail_pattern_initial, resultlen); + else + + /* + * The old_str did not satisfy the condition and it cannot + * be extended further. "Freeze" it. + */ + resultlen = freeze_pattern(old, old_info, + new_str_set, pattern, resultlen); + } + } + /* we no longer need old string set */ + string_set_discard(old_str_set); + } + return new_str_set; +} + +/* + * add_pattern + * + * Make a copy of 'old' (along with 'old_info' flag) and add new pattern char + * 'c' to it. Then add it to 'new_str_set'. 'pattern' and + * 'tail_pattern_initial' is checked to determine whether the copy is worth to + * add to new_str_set or not. The match length (possibly longer than + * 'resultlen') is returned. + */ +static +int +add_pattern(StringInfo old, int old_info, StringSet *new_str_set, char c, + char *pattern, char tail_pattern_initial, int resultlen) +{ + StringInfo new; + int info; + int len; + + /* + * New char in the input row satisfies the condition above. + */ + new = makeStringInfo(); /* copy source string */ + enlargeStringInfo(new, old->len + 1); + appendStringInfoString(new, old->data); + + /* add pattern variable char */ + appendStringInfoChar(new, c); + + /* + * Adhoc optimization. If the first letter in the input string is in the + * head and second position and there's no associated quatifier '+', then + * we can dicard the input because there's no chance to expand the string + * further. + * + * For example, pattern "abc" cannot match "aa". + */ + if (pattern[1] == new->data[0] && + pattern[1] == new->data[1] && + pattern[2] != '+' && + pattern[1] != pattern[2]) + { + destroyStringInfo(new); + return resultlen; + } + + info = old_info; + + /* + * Check if we can apply "tail pattern initial optimization". If the last + * regexp component in pattern has '+' quantifier, the component is set to + * the last pattern initial. For example if pattern is "ab+", + * tail_pattern_initial will become 'b'. Otherwise, tail_pattern_initial + * is '\0'. If the tail pattern initial optimization is possible, we do + * not need to apply regular expression match again. Suppose we have the + * previous string ended with "b" and the it was confirmed the regular + * expression match, then char 'b' can be added to the string without + * applying the regular expression match again. + */ + if (c == tail_pattern_initial) /* tail pattern initial optimization + * possible? */ + { + /* + * Is already confirmed to be matched with pattern? + */ + if ((info & STRSET_MATCHED) == 0) + { + /* not confirmed yet */ + len = do_pattern_match(pattern, new->data, new->len); + if (len > 0) + info = STRSET_MATCHED; /* set already confirmed flag */ + } + else + + /* + * already confirmed. Use the string length as the matching length + */ + len = new->len; + + /* update the longest match length if needed */ + if (len > resultlen) + resultlen = len; + } + + /* add new StringInfo to the string set */ + string_set_add(new_str_set, new, info); + + return resultlen; +} + +/* + * freeze_pattern + * + * "Freeze" 'old' (along with 'old_info' flag) and add it to + * 'new_str_set'. Frozen string is known to not be expanded further. The frozen + * string is check if it satisfies 'pattern'. If it does not, "discarded" + * mark is added. The discarded mark is also added if the match length is + * shorter than the current longest match length. The match length (possibly + * longer than 'resultlen') is returned. + */ +static +int +freeze_pattern(StringInfo old, int old_info, StringSet *new_str_set, + char *pattern, int resultlen) +{ + int len; + StringInfo new; + int new_str_size; + int new_index; + + /* + * We are freezing this pattern string. If the pattern string length is + * shorter than the current longest string length, we don't need to keep + * it. + */ + if (old->len < resultlen) + return resultlen; + + if (old_info & STRSET_MATCHED) + /* we don't need to apply pattern match again */ + len = old->len; + else + { + /* apply pattern match */ + len = do_pattern_match(pattern, old->data, old->len); + if (len <= 0) + { + /* no match. we can discard it */ + return resultlen; + } + } + if (len < resultlen) + { + /* shorter match. we can discard it */ + return resultlen; + } + + /* + * Match length is the longest so far + */ + resultlen = len; /* remember the longest match */ + + /* freeze the pattern string */ + new = makeStringInfo(); + enlargeStringInfo(new, old->len + 1); + appendStringInfoString(new, old->data); + /* set frozen mark */ + string_set_add(new_str_set, new, STRSET_FROZEN); + + /* + * Search new_str_set to find out frozen entries that have shorter match + * length. Mark them as "discard" so that they are discarded in the next + * round. + */ + new_str_size = + string_set_get_size(new_str_set) - 1; + + /* loop over new_str_set */ + for (new_index = 0; new_index < new_str_size; new_index++) + { + int info; + + new = string_set_get(new_str_set, new_index, &info); + + /* + * If this is frozen and is not longer than the current longest match + * length, we don't need to keep this. + */ + if (info & STRSET_FROZEN && new->len < resultlen) + { + /* + * mark this set to discard in the next round + */ + info |= STRSET_DISCARDED; + new_str_set->info[new_index] = info; + } + } + return resultlen; +} + +/* + * do_pattern_match + * + * Perform pattern match using 'pattern' against 'encoded_str' whose length is + * 'len' bytes (without null terminate). Returns matching number of rows if + * matching is succeeded. Otherwise returns 0. + */ +static +int +do_pattern_match(char *pattern, char *encoded_str, int len) +{ + static regex_t *regcache = NULL; + static regex_t preg; + static char patbuf[1024]; /* most recent 'pattern' is cached here */ + int plen; + int cflags = REG_EXTENDED; + size_t nmatch = 1; + int eflags = 0; + regmatch_t pmatch[1]; + int sts; + pg_wchar *data; + int data_len; + + /* + * Compile regexp if cache does not exist or existing cache is not same as + * "pattern". + */ + if (strcmp(patbuf, pattern)) + { + /* + * The compiled re must live in top memory context because patbuf is + * static data. + */ + MemoryContext oldContext = MemoryContextSwitchTo(TopMemoryContext); + + if (regcache != NULL) + pg_regfree(regcache); /* free previous re */ + + /* we need to convert to char to pg_wchar */ + plen = strlen(pattern); + data = (pg_wchar *) palloc((plen + 1) * sizeof(pg_wchar)); + data_len = pg_mb2wchar_with_len(pattern, data, plen); + /* compile re */ + sts = pg_regcomp(&preg, /* compiled re */ + data, /* target pattern */ + data_len, /* length of pattern */ + cflags, /* compile option */ + C_COLLATION_OID /* collation */ + ); + pfree(data); + + MemoryContextSwitchTo(oldContext); + + if (sts != REG_OKAY) + { + /* re didn't compile (no need for pg_regfree, if so) */ + ereport(ERROR, + (errcode(ERRCODE_INVALID_REGULAR_EXPRESSION), + errmsg("invalid regular expression: %s", pattern))); + } + + /* save cache */ + regcache = &preg; + strncpy(patbuf, pattern, sizeof(patbuf)); + } + + data = (pg_wchar *) palloc((len + 1) * sizeof(pg_wchar)); + data_len = pg_mb2wchar_with_len(encoded_str, data, len); + + /* execute the regular expression match */ + sts = pg_regexec( + &preg, /* compiled re */ + data, /* target string */ + data_len, /* length of encoded_str */ + 0, /* search start */ + NULL, /* rm details */ + nmatch, /* number of match sub re */ + pmatch, /* match result details */ + eflags); + + pfree(data); + + if (sts != REG_OKAY) + { + if (sts != REG_NOMATCH) + { + char errMsg[100]; + + pg_regerror(sts, &preg, errMsg, sizeof(errMsg)); + ereport(ERROR, + (errcode(ERRCODE_INVALID_REGULAR_EXPRESSION), + errmsg("regular expression failed: %s", errMsg))); + } + return 0; /* does not match */ + } + + len = pmatch[0].rm_eo; /* return match length */ + return len; + +} + +/* + * evaluate_pattern + * + * Evaluate expression associated with PATTERN variable vname. current_pos is + * relative row position in a frame (starting from 0). If vname is evaluated + * to true, initial letters associated with vname is appended to + * encode_str. result is out paramater representing the expression evaluation + * result is true of false. + *--------- + * Return values are: + * >=0: the last match absolute row position + * otherwise out of frame. + *--------- + */ +static +int64 +evaluate_pattern(WindowObject winobj, int64 current_pos, + char *vname, StringInfo encoded_str, bool *result) +{ + WindowAggState *winstate = winobj->winstate; + ExprContext *econtext = winstate->ss.ps.ps_ExprContext; + ListCell *lc1, + *lc2, + *lc3; + ExprState *pat; + Datum eval_result; + bool out_of_frame = false; + bool isnull; + TupleTableSlot *slot; + + forthree(lc1, winstate->defineVariableList, + lc2, winstate->defineClauseList, + lc3, winstate->defineInitial) + { + char initial; /* initial letter associated with vname */ + char *name = strVal(lfirst(lc1)); + + if (strcmp(vname, name)) + continue; + + initial = *(strVal(lfirst(lc3))); + + /* set expression to evaluate */ + pat = lfirst(lc2); + + /* get current, previous and next tuples */ + if (!get_slots(winobj, current_pos)) + { + out_of_frame = true; + } + else + { + /* evaluate the expression */ + eval_result = ExecEvalExpr(pat, econtext, &isnull); + if (isnull) + { + /* expression is NULL */ +#ifdef RPR_DEBUG + elog(DEBUG1, "expression for %s is NULL at row: " INT64_FORMAT, + vname, current_pos); +#endif + *result = false; + } + else + { + if (!DatumGetBool(eval_result)) + { + /* expression is false */ +#ifdef RPR_DEBUG + elog(DEBUG1, "expression for %s is false at row: " INT64_FORMAT, + vname, current_pos); +#endif + *result = false; + } + else + { + /* expression is true */ +#ifdef RPR_DEBUG + elog(DEBUG1, "expression for %s is true at row: " INT64_FORMAT, + vname, current_pos); +#endif + appendStringInfoChar(encoded_str, initial); + *result = true; + } + } + + slot = winstate->temp_slot_1; + if (slot != winstate->null_slot) + ExecClearTuple(slot); + slot = winstate->prev_slot; + if (slot != winstate->null_slot) + ExecClearTuple(slot); + slot = winstate->next_slot; + if (slot != winstate->null_slot) + ExecClearTuple(slot); + + break; + } + + if (out_of_frame) + { + *result = false; + return -1; + } + } + return current_pos; +} + +/* + * get_slots + * + * Get current, previous and next tuples. + * Returns false if current row is out of partition/full frame. + */ +static +bool +get_slots(WindowObject winobj, int64 current_pos) +{ + WindowAggState *winstate = winobj->winstate; + TupleTableSlot *slot; + int ret; + ExprContext *econtext; + + econtext = winstate->ss.ps.ps_ExprContext; + + /* set up current row tuple slot */ + slot = winstate->temp_slot_1; + if (!window_gettupleslot(winobj, current_pos, slot)) + { +#ifdef RPR_DEBUG + elog(DEBUG1, "current row is out of partition at:" INT64_FORMAT, + current_pos); +#endif + return false; + } + ret = row_is_in_frame(winstate, current_pos, slot); + if (ret <= 0) + { +#ifdef RPR_DEBUG + elog(DEBUG1, "current row is out of frame at: " INT64_FORMAT, + current_pos); +#endif + ExecClearTuple(slot); + return false; + } + econtext->ecxt_outertuple = slot; + + /* for PREV */ + if (current_pos > 0) + { + slot = winstate->prev_slot; + if (!window_gettupleslot(winobj, current_pos - 1, slot)) + { +#ifdef RPR_DEBUG + elog(DEBUG1, "previous row is out of partition at: " INT64_FORMAT, + current_pos - 1); +#endif + econtext->ecxt_scantuple = winstate->null_slot; + } + else + { + ret = row_is_in_frame(winstate, current_pos - 1, slot); + if (ret <= 0) + { +#ifdef RPR_DEBUG + elog(DEBUG1, "previous row is out of frame at: " INT64_FORMAT, + current_pos - 1); +#endif + ExecClearTuple(slot); + econtext->ecxt_scantuple = winstate->null_slot; + } + else + { + econtext->ecxt_scantuple = slot; + } + } + } + else + econtext->ecxt_scantuple = winstate->null_slot; + + /* for NEXT */ + slot = winstate->next_slot; + if (!window_gettupleslot(winobj, current_pos + 1, slot)) + { +#ifdef RPR_DEBUG + elog(DEBUG1, "next row is out of partiton at: " INT64_FORMAT, + current_pos + 1); +#endif + econtext->ecxt_innertuple = winstate->null_slot; + } + else + { + ret = row_is_in_frame(winstate, current_pos + 1, slot); + if (ret <= 0) + { +#ifdef RPR_DEBUG + elog(DEBUG1, "next row is out of frame at: " INT64_FORMAT, + current_pos + 1); +#endif + ExecClearTuple(slot); + econtext->ecxt_innertuple = winstate->null_slot; + } + else + econtext->ecxt_innertuple = slot; + } + return true; +} + +/* + * pattern_initial + * + * Return pattern variable initial character + * matching with pattern variable name vname. + * If not found, return 0. + */ +static +char +pattern_initial(WindowAggState *winstate, char *vname) +{ + char initial; + char *name; + ListCell *lc1, + *lc2; + + forboth(lc1, winstate->defineVariableList, + lc2, winstate->defineInitial) + { + name = strVal(lfirst(lc1)); /* DEFINE variable name */ + initial = *(strVal(lfirst(lc2))); /* DEFINE variable initial */ + + + if (!strcmp(name, vname)) + return initial; /* found */ + } + return 0; +} + +/* + * string_set_init + * + * Create dynamic set of StringInfo. + */ +static +StringSet * +string_set_init(void) +{ +/* Initial allocation size of str_set */ +#define STRING_SET_ALLOC_SIZE 1024 + + StringSet *string_set; + Size set_size; + + string_set = palloc0(sizeof(StringSet)); + string_set->set_index = 0; + set_size = STRING_SET_ALLOC_SIZE; + string_set->str_set = palloc(set_size * sizeof(StringInfo)); + string_set->info = palloc0(set_size * sizeof(int)); + string_set->set_size = set_size; + + return string_set; +} + +/* + * string_set_add + * + * Add StringInfo str to StringSet string_set. + */ +static +void +string_set_add(StringSet *string_set, StringInfo str, int info) +{ + Size set_size; + Size old_set_size; + + set_size = string_set->set_size; + if (string_set->set_index >= set_size) + { + old_set_size = set_size; + set_size *= 2; + string_set->str_set = repalloc(string_set->str_set, + set_size * sizeof(StringInfo)); + string_set->info = repalloc0(string_set->info, + old_set_size * sizeof(int), + set_size * sizeof(int)); + string_set->set_size = set_size; + } + + string_set->info[string_set->set_index] = info; + string_set->str_set[string_set->set_index++] = str; + + return; +} + +/* + * string_set_get + * + * Returns StringInfo specified by index. + * If there's no data yet, returns NULL. + */ +static +StringInfo +string_set_get(StringSet *string_set, int index, int *info) +{ + *info = 0; + + /* no data? */ + if (index == 0 && string_set->set_index == 0) + return NULL; + + if (index < 0 || index >= string_set->set_index) + elog(ERROR, "invalid index: %d", index); + + *info = string_set->info[index]; + + return string_set->str_set[index]; +} + +/* + * string_set_get_size + * + * Returns the size of StringSet. + */ +static +int +string_set_get_size(StringSet *string_set) +{ + return string_set->set_index; +} + +/* + * string_set_discard + * Discard StringSet. + * All memory including StringSet itself is freed. + */ +static +void +string_set_discard(StringSet *string_set) +{ + int i; + + for (i = 0; i < string_set->set_index; i++) + { + StringInfo str = string_set->str_set[i]; + + if (str) + destroyStringInfo(str); + } + pfree(string_set->info); + pfree(string_set->str_set); + pfree(string_set); +} + +/* + * variable_pos_init + * + * Create and initialize variable postion structure + */ +static +VariablePos * +variable_pos_init(void) +{ + VariablePos *variable_pos; + + variable_pos = palloc(sizeof(VariablePos) * NUM_ALPHABETS); + MemSet(variable_pos, -1, sizeof(VariablePos) * NUM_ALPHABETS); + return variable_pos; +} + +/* + * variable_pos_register + * + * Register pattern variable whose initial is initial into postion index. + * pos is position of initial. + * If pos is already registered, register it at next empty slot. + */ +static +void +variable_pos_register(VariablePos *variable_pos, char initial, int pos) +{ + int index = initial - 'a'; + int slot; + int i; + + if (pos < 0 || pos > NUM_ALPHABETS) + elog(ERROR, "initial is not valid char: %c", initial); + + for (i = 0; i < NUM_ALPHABETS; i++) + { + slot = variable_pos[index].pos[i]; + if (slot < 0) + { + /* empty slot found */ + variable_pos[index].pos[i] = pos; + return; + } + } + elog(ERROR, "no empty slot for initial: %c", initial); +} + +/* + * variable_pos_compare + * + * Returns true if initial1 can be followed by initial2 + */ +static +bool +variable_pos_compare(VariablePos *variable_pos, char initial1, char initial2) +{ + int index1, + index2; + int pos1, + pos2; + + for (index1 = 0;; index1++) + { + pos1 = variable_pos_fetch(variable_pos, initial1, index1); + if (pos1 < 0) + break; + + for (index2 = 0;; index2++) + { + pos2 = variable_pos_fetch(variable_pos, initial2, index2); + if (pos2 < 0) + break; + if (pos1 <= pos2) + return true; + } + } + return false; +} + +/* + * variable_pos_fetch + * + * Fetch position of pattern variable whose initial is initial, and whose index + * is index. If no postion was registered by initial, index, returns -1. + */ +static +int +variable_pos_fetch(VariablePos *variable_pos, char initial, int index) +{ + int pos = initial - 'a'; + + if (pos < 0 || pos > NUM_ALPHABETS) + elog(ERROR, "initial is not valid char: %c", initial); + + if (index < 0 || index > NUM_ALPHABETS) + elog(ERROR, "index is not valid: %d", index); + + return variable_pos[pos].pos[index]; +} + +/* + * variable_pos_build + * + * Build VariablePos structure and return it. + */ +static +VariablePos * +variable_pos_build(WindowAggState *winstate) +{ + VariablePos *variable_pos; + StringInfo pattern_str; + int initial_index = 0; + ListCell *lc1, + *lc2; + + variable_pos = winstate->variable_pos = variable_pos_init(); + pattern_str = winstate->pattern_str = makeStringInfo(); + appendStringInfoChar(pattern_str, '^'); + + forboth(lc1, winstate->patternVariableList, + lc2, winstate->patternRegexpList) + { + char *vname = strVal(lfirst(lc1)); + char *quantifier = strVal(lfirst(lc2)); + char initial; + + initial = pattern_initial(winstate, vname); + Assert(initial != 0); + appendStringInfoChar(pattern_str, initial); + if (quantifier[0]) + appendStringInfoChar(pattern_str, quantifier[0]); + + /* + * Register the initial at initial_index. If the initial appears more + * than once, all of it's initial_index will be recorded. This could + * happen if a pattern variable appears in the PATTERN clause more + * than once like "UP DOWN UP" "UP UP UP". + */ + variable_pos_register(variable_pos, initial, initial_index); + + initial_index++; + } + + return variable_pos; +} diff --git a/src/backend/utils/adt/windowfuncs.c b/src/backend/utils/adt/windowfuncs.c index 473c61569f..3142a8bc06 100644 --- a/src/backend/utils/adt/windowfuncs.c +++ b/src/backend/utils/adt/windowfuncs.c @@ -13,6 +13,9 @@ */ #include "postgres.h" +#include "catalog/pg_collation_d.h" +#include "executor/executor.h" +#include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "nodes/supportnodes.h" #include "utils/fmgrprotos.h" @@ -37,11 +40,19 @@ typedef struct int64 remainder; /* (total rows) % (bucket num) */ } ntile_context; +/* + * rpr process information. + * Used for AFTER MATCH SKIP PAST LAST ROW + */ +typedef struct SkipContext +{ + int64 pos; /* last row absolute position */ +} SkipContext; + static bool rank_up(WindowObject winobj); static Datum leadlag_common(FunctionCallInfo fcinfo, bool forward, bool withoffset, bool withdefault); - /* * utility routine for *_rank functions. */ @@ -674,7 +685,7 @@ window_last_value(PG_FUNCTION_ARGS) bool isnull; result = WinGetFuncArgInFrame(winobj, 0, - 0, WINDOW_SEEK_TAIL, true, + 0, WINDOW_SEEK_TAIL, false, &isnull, NULL); if (isnull) PG_RETURN_NULL(); @@ -714,3 +725,25 @@ window_nth_value(PG_FUNCTION_ARGS) PG_RETURN_DATUM(result); } + +/* + * prev + * Dummy function to invoke RPR's navigation operator "PREV". + * This is *not* a window function. + */ +Datum +window_prev(PG_FUNCTION_ARGS) +{ + PG_RETURN_DATUM(PG_GETARG_DATUM(0)); +} + +/* + * next + * Dummy function to invoke RPR's navigation operation "NEXT". + * This is *not* a window function. + */ +Datum +window_next(PG_FUNCTION_ARGS) +{ + PG_RETURN_DATUM(PG_GETARG_DATUM(0)); +} diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 2dcc2d42da..ee11ee2c8b 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10664,6 +10664,12 @@ { oid => '3114', descr => 'fetch the Nth row value', proname => 'nth_value', prokind => 'w', prorettype => 'anyelement', proargtypes => 'anyelement int4', prosrc => 'window_nth_value' }, +{ oid => '8126', descr => 'previous value', + proname => 'prev', provolatile => 's', prorettype => 'anyelement', + proargtypes => 'anyelement', prosrc => 'window_prev' }, +{ oid => '8127', descr => 'next value', + proname => 'next', provolatile => 's', prorettype => 'anyelement', + proargtypes => 'anyelement', prosrc => 'window_next' }, # functions for range types { oid => '3832', descr => 'I/O', diff --git a/src/include/nodes/execnodes.h b/src/include/nodes/execnodes.h index 1590b64392..f96782fd6a 100644 --- a/src/include/nodes/execnodes.h +++ b/src/include/nodes/execnodes.h @@ -2585,6 +2585,37 @@ typedef enum WindowAggStatus * tuples during spool */ } WindowAggStatus; +#define RF_NOT_DETERMINED 0 +#define RF_FRAME_HEAD 1 +#define RF_SKIPPED 2 +#define RF_UNMATCHED 3 + +/* + * Allowed PATTERN variables positions. + * Used in RPR. + * + * pos represents the pattern variable defined order in DEFINE caluase. For + * example. "DEFINE START..., UP..., DOWN ..." and "PATTERN START UP DOWN UP" + * will create: + * VariablePos[0].pos[0] = 0; START + * VariablePos[1].pos[0] = 1; UP + * VariablePos[1].pos[1] = 3; UP + * VariablePos[2].pos[0] = 2; DOWN + * + * Note that UP has two pos because UP appears in PATTERN twice. + * + * By using this strucrture, we can know which pattern variable can be followed + * by which pattern variable(s). For example, START can be followed by UP and + * DOWN since START's pos is 0, and UP's pos is 1 or 3, DOWN's pos is 2. + * DOWN can be followed by UP since UP's pos is either 1 or 3. + * + */ +#define NUM_ALPHABETS 26 /* we allow [a-z] variable initials */ +typedef struct VariablePos +{ + int pos[NUM_ALPHABETS]; /* postions in PATTERN */ +} VariablePos; + typedef struct WindowAggState { ScanState ss; /* its first field is NodeTag */ @@ -2644,6 +2675,21 @@ typedef struct WindowAggState int64 groupheadpos; /* current row's peer group head position */ int64 grouptailpos; /* " " " " tail position (group end+1) */ + /* these fields are used in Row pattern recognition: */ + RPSkipTo rpSkipTo; /* Row Pattern Skip To type */ + List *patternVariableList; /* list of row pattern variables names + * (list of String) */ + List *patternRegexpList; /* list of row pattern regular expressions + * ('+' or ''. list of String) */ + List *defineVariableList; /* list of row pattern definition + * variables (list of String) */ + List *defineClauseList; /* expression for row pattern definition + * search conditions ExprState list */ + List *defineInitial; /* list of row pattern definition variable + * initials (list of String) */ + VariablePos *variable_pos; /* list of pattern variable positions */ + StringInfo pattern_str; /* PATTERN initials */ + MemoryContext partcontext; /* context for partition-lifespan data */ MemoryContext aggcontext; /* shared context for aggregate working data */ MemoryContext curaggcontext; /* current aggregate's working data */ @@ -2671,6 +2717,18 @@ typedef struct WindowAggState TupleTableSlot *agg_row_slot; TupleTableSlot *temp_slot_1; TupleTableSlot *temp_slot_2; + + /* temporary slots for RPR */ + TupleTableSlot *prev_slot; /* PREV row navigation operator */ + TupleTableSlot *next_slot; /* NEXT row navigation operator */ + TupleTableSlot *null_slot; /* all NULL slot */ + + /* + * Each byte corresponds to a row positioned at absolute its pos in + * partition. See above definition for RF_* + */ + char *reduced_frame_map; + int64 alloc_sz; /* size of the map */ } WindowAggState; /* ---------------- -- 2.25.1 ----Next_Part(Tue_Dec_31_08_57_07_2024_963)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v27-0006-Row-pattern-recognition-patch-docs.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 274ad900c65..5188244dfd6 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -993,6 +993,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0f6b5df322c..23511a0905a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --3n3vqr5y2jhknrqj Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v49-0007-WIP-add-max_repack_replication_slots.patch" ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 21ab81c6f7f..42165c5552e 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --mdsv5bdgfjjj6d77-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 140 insertions(+), 23 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 018e9f7b013..423cea26b0b 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1075,6 +1075,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..b02ec4e8c3e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..c785a3db59f 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1370,9 +1373,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 1dad125706e..c6693b93a65 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -69,10 +69,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --gwom7bl7ogtszo4k-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 7291b4180ab..0103bc10bd1 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --cldir6umqisr673d-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 065316ee866..77c206ff944 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1084,6 +1084,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --nzintiedl6o4kcyp-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 74 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 8 files changed, 137 insertions(+), 21 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..b96b73d51d3 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 3acb2e1d2ba..74faa4f5582 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..6dd4fa7dcc0 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2688,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2703,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2712,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2733,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2755,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2774,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2827,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2849,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..9e6e7b18786 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --2fxmamo6mu2qbxgv-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/cluster.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 38 ++++++++--- src/backend/storage/ipc/procarray.c | 73 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 6 +- src/include/access/xlog_internal.h | 2 +- src/include/storage/proc.h | 3 +- src/include/storage/standby.h | 3 + src/include/storage/standbydefs.h | 2 + 10 files changed, 138 insertions(+), 22 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..79c052d3607 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXid %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f5c9a34374d..d050b0b1444 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8477,6 +8478,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 4fd10a5e7b3..73407c383da 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1086,6 +1086,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is + * o.k. for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..fbdd4600a2b 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This * means all transactions starting afterwards have enough information to * be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is + * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXidLogical is * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all * transactions that are currently in progress have a catalog snapshot, * and all their changes have been collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1459,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index 0f913897acc..f1a03e6a754 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,24 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2672,13 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2687,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2702,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2711,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2732,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2754,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2773,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2826,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2848,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index f3ad90c7c7a..5c4121fcbc8 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1188,6 +1188,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1358,10 +1359,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1372,7 +1375,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) /* array of TransactionIds */ if (xlrec.xcnt > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h index 629ac3a7d3e..1730b07810f 100644 --- a/src/include/access/xlog_internal.h +++ b/src/include/access/xlog_internal.h @@ -31,7 +31,7 @@ /* * Each page of XLOG file has a header like this: */ -#define XLOG_PAGE_MAGIC 0xD11D /* can be used as WAL version indicator */ +#define XLOG_PAGE_MAGIC 0xD11E /* can be used as WAL version indicator */ typedef struct XLogPageHeaderData { diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index bf3094f0f7d..120370f459d 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -67,10 +67,11 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_REPACK 0x40 /* currently REPACK (CONCURRENTLY) */ /* flags reset at EOXact */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | PROC_IN_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index c63a4f2cc6a..0bd28e270f1 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -124,10 +124,13 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK + * (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
* [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). @ 2026-03-17 19:22 Antonin Houska <[email protected]> 0 siblings, 0 replies; 1066+ messages in thread From: Antonin Houska @ 2026-03-17 19:22 UTC (permalink / raw) During logical decoding, we need to know if particular transaction performed catalog changes because catalog information is needed to construct heap tuples. To be sure that we have enough information of each transaction, the logical decoding cannot start before all the already running transactions have completed. The problem with REPACK (CONCURRENTLY) is that it has XID assigned and writes WAL records marked with it. Thus if another backend runs REPACK (CONCURRENTLY) and tries to setup the logical decoding, it has to wait for the completion of all the other transactions involved in REPACK (CONCURRENTLY). However, REPACK (CONCURRENTLY) does not perform any catalog changes relevant to logical decoding, so the other backends executing this command can ignore it. This patch implements it by adding information about transactions executing the command to the xl_running_xacts WAL record, and by teaching the snapshot builder to use the information. --- src/backend/access/rmgrdesc/standbydesc.c | 15 ++++- src/backend/access/transam/xlog.c | 2 + src/backend/commands/repack.c | 16 +++++ src/backend/replication/logical/snapbuild.c | 51 +++++++++----- src/backend/storage/ipc/procarray.c | 75 +++++++++++++++++++-- src/backend/storage/ipc/standby.c | 8 ++- src/include/storage/standby.h | 2 + src/include/storage/standbydefs.h | 2 + 8 files changed, 144 insertions(+), 27 deletions(-) diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c index 0a291354ae2..58ebecf4927 100644 --- a/src/backend/access/rmgrdesc/standbydesc.c +++ b/src/backend/access/rmgrdesc/standbydesc.c @@ -21,10 +21,11 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) { int i; - appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u", + appendStringInfo(buf, "nextXid %u latestCompletedXid %u oldestRunningXid %u oldestRunningXidLogical %u", xlrec->nextXid, xlrec->latestCompletedXid, - xlrec->oldestRunningXid); + xlrec->oldestRunningXid, + xlrec->oldestRunningXidLogical); if (xlrec->xcnt > 0) { appendStringInfo(buf, "; %d xacts:", xlrec->xcnt); @@ -41,6 +42,16 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec) for (i = 0; i < xlrec->subxcnt; i++) appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]); } + + if (xlrec->xcnt_repack > 0) + { + TransactionId *xids_repack; + + appendStringInfo(buf, "; %d xacts_repack:", xlrec->xcnt_repack); + xids_repack = xlrec->xids + xlrec->xcnt + xlrec->subxcnt; + for (i = 0; i < xlrec->xcnt_repack; i++) + appendStringInfo(buf, " %u", xids_repack[i]); + } } void diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 2c1c6f88b74..f1cbdee7618 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -5912,6 +5912,7 @@ StartupXLOG(void) * subxids are listed with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); @@ -8483,6 +8484,7 @@ xlog_redo(XLogReaderState *record) * with their parent prepared transactions. */ running.xcnt = nxids; + running.xcnt_repack = 0; running.subxcnt = 0; running.subxid_status = SUBXIDS_IN_SUBTRANS; running.nextXid = XidFromFullTransactionId(checkPoint.nextXid); diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 781a471fc1d..29ba49744eb 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -988,6 +988,22 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, if (concurrent) { + /* + * Do not let other backends wait for our completion during their + * setup of logical replication. Unlike logical replication publisher, + * we will have XID assigned, so the other backends - whether + * walsenders involved in logical replication or regular backends + * executing also REPACK (CONCURRENTLY) - would have to wait for our + * completion before they can build their initial snapshot. It is o.k. + * for any decoding backend to ignore us because we do not change + * tuple descriptor of any table, and the data changes we write should + * not be decoded by other backends. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + /* * The worker needs to be member of the locking group we're the leader * of. We ought to become the leader before the worker starts. The diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 9cf499ce7c6..f2008c6877c 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1172,7 +1172,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact * xmin, which looks odd but is correct and actually more efficient, since * we hit fast paths in heapam_visibility.c. */ - builder->xmin = running->oldestRunningXid; + builder->xmin = running->oldestRunningXidLogical; /* Remove transactions we don't need to keep track off anymore */ SnapBuildPurgeOlderTxn(builder); @@ -1188,9 +1188,9 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ xmin = ReorderBufferGetOldestXmin(builder->reorder); if (xmin == InvalidTransactionId) - xmin = running->oldestRunningXid; + xmin = running->oldestRunningXidLogical; elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u", - builder->xmin, builder->xmax, running->oldestRunningXid, xmin); + builder->xmin, builder->xmax, running->oldestRunningXidLogical, xmin); LogicalIncreaseXminForSlot(lsn, xmin); /* @@ -1275,14 +1275,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * have all necessary catalog rows anymore. */ if (TransactionIdIsNormal(builder->initial_xmin_horizon) && - NormalTransactionIdPrecedes(running->oldestRunningXid, + NormalTransactionIdPrecedes(running->oldestRunningXidLogical, builder->initial_xmin_horizon)) { ereport(DEBUG1, errmsg_internal("skipping snapshot at %X/%08X while building logical decoding snapshot, xmin horizon too low", LSN_FORMAT_ARGS(lsn)), errdetail_internal("initial xmin horizon of %u vs the snapshot's %u", - builder->initial_xmin_horizon, running->oldestRunningXid)); + builder->initial_xmin_horizon, running->oldestRunningXidLogical)); SnapBuildWaitSnapshot(running, builder->initial_xmin_horizon); @@ -1299,7 +1299,7 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn * NB: We might have already started to incrementally assemble a snapshot, * so we need to be careful to deal with that. */ - if (running->oldestRunningXid == running->nextXid) + if (running->oldestRunningXidLogical == running->nextXid) { if (!XLogRecPtrIsValid(builder->start_decoding_at) || builder->start_decoding_at <= lsn) @@ -1378,14 +1378,14 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from BUILDING_SNAPSHOT to FULL_SNAPSHOT. * - * In BUILDING_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid - * is >= than nextXid from when we switched to BUILDING_SNAPSHOT. This - * means all transactions starting afterwards have enough information to - * be decoded. Switch to FULL_SNAPSHOT. + * In BUILDING_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * BUILDING_SNAPSHOT. This means all transactions starting afterwards + * have enough information to be decoded. Switch to FULL_SNAPSHOT. */ else if (builder->state == SNAPBUILD_BUILDING_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_FULL_SNAPSHOT; builder->next_phase_at = running->nextXid; @@ -1402,14 +1402,15 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn /* * c) transition from FULL_SNAPSHOT to CONSISTENT. * - * In FULL_SNAPSHOT state, and this xl_running_xacts' oldestRunningXid is - * >= than nextXid from when we switched to FULL_SNAPSHOT. This means all - * transactions that are currently in progress have a catalog snapshot, - * and all their changes have been collected. Switch to CONSISTENT. + * In FULL_SNAPSHOT state, and this xl_running_xacts' + * oldestRunningXidLogical is >= than nextXid from when we switched to + * FULL_SNAPSHOT. This means all transactions that are currently in + * progress have a catalog snapshot, and all their changes have been + * collected. Switch to CONSISTENT. */ else if (builder->state == SNAPBUILD_FULL_SNAPSHOT && TransactionIdPrecedesOrEquals(builder->next_phase_at, - running->oldestRunningXid)) + running->oldestRunningXidLogical)) { builder->state = SNAPBUILD_CONSISTENT; builder->next_phase_at = InvalidTransactionId; @@ -1459,6 +1460,24 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff) if (TransactionIdFollows(xid, cutoff)) continue; + /* Do not wait for transactions running REPACK (CONCURRENTLY). */ + if (running->xcnt_repack > 0) + { + TransactionId *xids_repack; + int i; + + xids_repack = running->xids + running->xcnt + running->subxcnt; + + for (i = 0; i < running->xcnt_repack; i++) + { + if (xid == xids_repack[i]) + break; + } + /* Found? */ + if (i < running->xcnt_repack) + continue; + } + XactLockTableWait(xid, NULL, NULL, XLTW_None); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index cc207cb56e3..033ae68b57e 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -2643,15 +2643,25 @@ GetRunningTransactionData(void) RunningTransactions CurrentRunningXacts = &CurrentRunningXactsData; TransactionId latestCompletedXid; TransactionId oldestRunningXid; + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; TransactionId *xids; int index; - int count; + int count, + count_repack; int subcount; bool suboverflowed; + TransactionId *xids_repack = NULL; + bool logical_decoding_enabled = IsLogicalDecodingEnabled(); Assert(!RecoveryInProgress()); + /* + * TODO Consider a GUC to reserve certain amount of replication slots for + * REPACK (CONCURRENTLY) and using it here. + */ +#define MAX_REPACK_XIDS 16 + /* * Allocating space for maxProcs xids is usually overkill; numProcs would * be sufficient. But it seems better to do the malloc while not holding @@ -2663,11 +2673,14 @@ GetRunningTransactionData(void) */ if (CurrentRunningXacts->xids == NULL) { + /* FIXME probably fails if logical decoding is enable on-the-fly */ + int nrepack = logical_decoding_enabled ? MAX_REPACK_XIDS : 0; + /* * First call */ CurrentRunningXacts->xids = (TransactionId *) - malloc(TOTAL_MAX_CACHED_SUBXIDS * sizeof(TransactionId)); + malloc((TOTAL_MAX_CACHED_SUBXIDS + nrepack) * sizeof(TransactionId)); if (CurrentRunningXacts->xids == NULL) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), @@ -2676,7 +2689,10 @@ GetRunningTransactionData(void) xids = CurrentRunningXacts->xids; - count = subcount = 0; + if (logical_decoding_enabled) + xids_repack = palloc_array(TransactionId, MAX_REPACK_XIDS); + + count = subcount = count_repack = 0; suboverflowed = false; /* @@ -2688,7 +2704,7 @@ GetRunningTransactionData(void) latestCompletedXid = XidFromFullTransactionId(TransamVariables->latestCompletedXid); - oldestDatabaseRunningXid = oldestRunningXid = + oldestDatabaseRunningXid = oldestRunningXid = oldestRunningXidLogical = XidFromFullTransactionId(TransamVariables->nextXid); /* @@ -2697,6 +2713,8 @@ GetRunningTransactionData(void) for (index = 0; index < arrayP->numProcs; index++) { TransactionId xid; + int pgprocno; + PGPROC *proc; /* Fetch xid just once - see GetNewTransactionId */ xid = UINT32_ACCESS_ONCE(other_xids[index]); @@ -2716,6 +2734,21 @@ GetRunningTransactionData(void) if (TransactionIdPrecedes(xid, oldestRunningXid)) oldestRunningXid = xid; + if (logical_decoding_enabled && + TransactionIdPrecedes(xid, oldestRunningXidLogical)) + { + /* + * Backends running REPACK concurrently need to be excluded from + * oldestRunningXidLogical, otherwise the snapshot builder cannot + * proceed in building the initial snapshot. + */ + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if ((proc->statusFlags & PROC_IN_CONCURRENT_REPACK) == 0) + oldestRunningXidLogical = xid; + } + /* * Also, update the oldest running xid within the current database. As * fetching pgprocno and PGPROC could cause cache misses, we do cheap @@ -2723,8 +2756,8 @@ GetRunningTransactionData(void) */ if (TransactionIdPrecedes(xid, oldestDatabaseRunningXid)) { - int pgprocno = arrayP->pgprocnos[index]; - PGPROC *proc = &allProcs[pgprocno]; + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; if (proc->databaseId == MyDatabaseId) oldestDatabaseRunningXid = xid; @@ -2742,6 +2775,19 @@ GetRunningTransactionData(void) */ xids[count++] = xid; + + /* + * Collect XIDSs of transactions running REPACK (CONCURRENTLY). + */ + if (logical_decoding_enabled && + count_repack < MAX_REPACK_XIDS) + { + pgprocno = arrayP->pgprocnos[index]; + proc = &allProcs[pgprocno]; + + if (proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + xids_repack[count_repack++] = xid; + } } /* @@ -2782,6 +2828,19 @@ GetRunningTransactionData(void) } } + /* + * Append the XIDs running REPACK (CONCURRENTLY), if any. + * + * XXX Should we sort the array and use bsearch() when using it? + */ + if (count_repack > 0) + { + for (int i = 0; i < count_repack; i++) + xids[count++] = xids_repack[i]; + } + if (xids_repack) + pfree(xids_repack); + /* * It's important *not* to include the limits set by slots here because * snapbuild.c uses oldestRunningXid to manage its xmin horizon. If those @@ -2791,11 +2850,13 @@ GetRunningTransactionData(void) * increases if slots do. */ - CurrentRunningXacts->xcnt = count - subcount; + CurrentRunningXacts->xcnt = count - subcount - count_repack; CurrentRunningXacts->subxcnt = subcount; + CurrentRunningXacts->xcnt_repack = count_repack; CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY; CurrentRunningXacts->nextXid = XidFromFullTransactionId(TransamVariables->nextXid); CurrentRunningXacts->oldestRunningXid = oldestRunningXid; + CurrentRunningXacts->oldestRunningXidLogical = oldestRunningXidLogical; CurrentRunningXacts->oldestDatabaseRunningXid = oldestDatabaseRunningXid; CurrentRunningXacts->latestCompletedXid = latestCompletedXid; diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c index de9092fdf5b..fd3e4fe31f3 100644 --- a/src/backend/storage/ipc/standby.c +++ b/src/backend/storage/ipc/standby.c @@ -1189,6 +1189,7 @@ standby_redo(XLogReaderState *record) RunningTransactionsData running; running.xcnt = xlrec->xcnt; + running.xcnt_repack = xlrec->xcnt_repack; running.subxcnt = xlrec->subxcnt; running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY; running.nextXid = xlrec->nextXid; @@ -1359,10 +1360,12 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRecPtr recptr; xlrec.xcnt = CurrRunningXacts->xcnt; + xlrec.xcnt_repack = CurrRunningXacts->xcnt_repack; xlrec.subxcnt = CurrRunningXacts->subxcnt; xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY); xlrec.nextXid = CurrRunningXacts->nextXid; xlrec.oldestRunningXid = CurrRunningXacts->oldestRunningXid; + xlrec.oldestRunningXidLogical = CurrRunningXacts->oldestRunningXidLogical; xlrec.latestCompletedXid = CurrRunningXacts->latestCompletedXid; /* Header */ @@ -1371,9 +1374,10 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts) XLogRegisterData(&xlrec, MinSizeOfXactRunningXacts); /* array of TransactionIds */ - if (xlrec.xcnt > 0) + if (xlrec.xcnt + xlrec.xcnt_repack > 0) XLogRegisterData(CurrRunningXacts->xids, - (xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId)); + (xlrec.xcnt + xlrec.xcnt_repack + xlrec.subxcnt) * + sizeof(TransactionId)); recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS); diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h index 6a314c693cd..fe4dcdc3def 100644 --- a/src/include/storage/standby.h +++ b/src/include/storage/standby.h @@ -127,10 +127,12 @@ typedef enum typedef struct RunningTransactionsData { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY). */ int subxcnt; /* # of subxact ids in xids[] */ subxids_array_status subxid_status; TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId oldestDatabaseRunningXid; /* same as above, but within the * current database */ TransactionId latestCompletedXid; /* so we can set xmax */ diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h index 231d251fd51..edad609fa9a 100644 --- a/src/include/storage/standbydefs.h +++ b/src/include/storage/standbydefs.h @@ -47,10 +47,12 @@ typedef struct xl_standby_locks typedef struct xl_running_xacts { int xcnt; /* # of xact ids in xids[] */ + int xcnt_repack; /* # of xacts running REPACK (CONCURRENTLY) */ int subxcnt; /* # of subxact ids in xids[] */ bool subxid_overflow; /* snapshot overflowed, subxids missing */ TransactionId nextXid; /* xid from TransamVariables->nextXid */ TransactionId oldestRunningXid; /* *not* oldestXmin */ + TransactionId oldestRunningXidLogical; TransactionId latestCompletedXid; /* so we can set xmax */ TransactionId xids[FLEXIBLE_ARRAY_MEMBER]; -- 2.47.3 --qfkt2ktdpcfeypib-- ^ permalink raw reply [nested|flat] 1066+ messages in thread
end of thread, other threads:[~2026-03-17 19:22 UTC | newest] Thread overview: 1066+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 2022-08-23 08:50 [PATCH v1] solaris: Use versioning scripts instead of -Bsymbolic Andres Freund <[email protected]> 2024-12-30 23:53 [PATCH v27 5/9] Row pattern recognition patch (executor). Tatsuo Ishii <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v49 6/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v46 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v44 10/10] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v45 8/8] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v43 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v47 9/9] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]> 2026-03-17 19:22 [PATCH v48 7/7] Teach snapshot builder to skip transactions running REPACK (CONCURRENTLY). Antonin Houska <[email protected]>
This inbox is served by agora; see mirroring instructions for how to clone and mirror all data and code used for this inbox